paper-with-me

Papers

Hybrid-Diffusion Models: Combining Open-loop Routines with Visuomotor Diffusion Policies

2025-12-04 · Jonne Van Haastregt, Bastian Orthmann, Michael C. Welle, Yuchong Zhang, Danica Kragic arxiv

Despite the fact that visuomotor-based policies obtained via imitation learning demonstrate good performances in complex manipulation tasks, they usually struggle to achieve the same accuracy and speed as traditional control based methods. In this work, we introduce Hybrid-Diffusion models that combine open-loop routines with visuomotor diffusion policies. We develop Teleoperation Augmentation Primitives (TAPs) that allow the operator to perform predefined routines, such as locking specific axes, moving to perching waypoints, or triggering task-specific routines seamlessly during demonstrations. Our Hybrid-Diffusion method learns to trigger such TAPs during inference. We validate the method on challenging real-world tasks: Vial Aspiration, Open-Container Liquid Transfer, and container unscrewing. All experimental videos are available on the project's website: https://hybriddiffusion.github.io/

📄 PDF Abstract BibTeX arXiv:2512.04960

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization

2026-08-08 · Víctor Gallego hf

In evolutionary algorithms powered by language models, the LLM acts as a single operator that simultaneously updates structural components (like control flow) and continuous parameters. While LLMs can be good at the firs…

Bayesian Inference

Goal-Oriented Reactive Simulation for Closed-Loop Trajectory Prediction

2026-03-25 · Harsh Yadav, Tobias Meisen arxiv

Current trajectory prediction models are primarily trained in an open-loop manner, which often leads to covariate shift and compounding errors when deployed in real-world, closed-loop settings. Furthermore, relying on st…

Trajectory PredictionCollision Avoidance

3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors

2024-03-04 · Fangzhou Hong, Jiaxiang Tang, Ziang Cao, Min Shi 외

We present a two-stage text-to-3D generation system, namely 3DTopia, which generates high-quality general 3D assets within 5 minutes using hybrid diffusion priors. The first stage samples from a 3D diffusion prior direct…

3D GenerationText to 3DTexture Synthesis

FLARE: Diffusion for Hybrid Language Model

2026-06-01 · Yuchen Zhu, Jing Shi, Chongjian Ge, Hao Tan 외 arxiv

Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficient-inference work has progressed along tw…

Hybrid Diffusion Model for Breast Ultrasound Image Augmentation

2026-03-27 · Farhan Fuad Abir, Sanjeda Sara Jennifer, Niloofar Yousefi, Laura J. Brattain arxiv

We propose a hybrid diffusion-based augmentation framework to overcome the critical challenge of ultrasound data augmentation in breast ultrasound (BUS) datasets. Unlike conventional diffusion-based augmentations, our ap…

Text-to-Image GenerationImage AugmentationData Augmentation